Job Description
Role: Application Production Support Engineer
\n
Location: Charlotte, NC (Hybrid role – 3 days/week)
\n
Exp : 8+ Years
\n
\n
Job Description
\n
Experienced Application Production Support Engineer with 1-2 years of experience supporting AI/LLM-driven applications in production environments. The ideal candidate should have hands-on experience in production support, incident management, monitoring, troubleshooting, and operational support for applications leveraging Generative AI and Large Language Models (LLMs).
\n
\n
Key Responsibilities:
\n
· Provide L2/L3 production support for applications utilizing Large Language Models (LLMs) and Generative AI technologies.
\n
· Monitor application health, performance, and availability using observability tools such as Splunk and Dynatrace.
\n
· Troubleshoot production issues related to AI applications, APIs, backend services, infrastructure, and databases.
\n
· Investigate and resolve incidents within SLA timelines, perform root cause analysis (RCA), and implement preventive measures.
\n
· Support and maintain Redis and MongoDB databases, ensuring optimal performance and availability.
\n
· Monitor LLM consumption metrics including Token Usage, Tokens Per Minute (TPM), Requests Per Minute (RPM), throttling limits, and rate limits.
\n
· Collaborate with development, infrastructure, cloud, and AI engineering teams to resolve complex production issues.
\n
· Support containerized workloads deployed on Kubernetes and/or OpenShift platforms.
\n
· Utilize LLM observability and evaluation platforms such as LangSmith, Galileo, or similar tools to analyze model behavior and performance.
\n
· Participate in production deployments, release activities, and change management processes.
\n
· Maintain operational runbooks, troubleshooting guides, and knowledge-base documentation.